Difference-in-Differences (DID)
From classic 2×2 to staggered adoption
The Intellectual Origins of DID: From the Cholera Map to Causal Inference
Tracing the historical lineage of difference-in-differences—from John Snow's London cholera study in the 19th century to a cornerstone of modern econometrics, and understanding how the core idea of DID was born.
Classic 2×2 Difference-in-Differences (DID): Model Specification, Estimation, and Inference
A systematic introduction to the classic difference-in-differences method, two-way fixed effects estimation, clustered standard error selection, with complete Stata code.
Event Study: Dynamic Effect Estimation and Coefficient Plots
A comprehensive guide to the event study method, covering dynamic effect estimation, coefficient plot construction, normalization, and Leads/Lags settings.
Parallel Trends Assumption: Intuition, Testing, and Visualization
An in-depth understanding of the core assumption of DID—parallel trends. Explains the meaning of the assumption, visualization testing methods, and pre-trend tests, with accompanying Stata code.
Staggered DID: TWFE Bias and New Estimators (CS/SA/BJS)
An in-depth explanation of TWFE bias in staggered DID designs, introducing the principles and practical implementation of three new estimators: Callaway-Sant'Anna, Sun-Abraham, and Borusyak-Jaravel-Spiess.
Popular articles (by visits)
- Event Study: Dynamic Effect Estimation and Coefficient Plots
A comprehensive guide to the event study method, covering dynamic effect estimation, coefficient plot construction, normalization, and Leads/Lags settings.
31 visits - Staggered DID: TWFE Bias and New Estimators (CS/SA/BJS)
An in-depth explanation of TWFE bias in staggered DID designs, introducing the principles and practical implementation of three new estimators: Callaway-Sant'Anna, Sun-Abraham, and Borusyak-Jaravel-Spiess.
21 visits